Header logo is ei


2013


no image
Maximum-Margin Framework for Training Data Synchronization in Large-Scale Hierarchical Classification

Babbar, R., Partalas, I., Gaussier, E., Amini, M.

In Neural Information Processing - 20th International Conference, Proceedings, Part I, Lecture Notes in Computer Science, Vol. 8226, pages: 336-343, (Editors: M Lee and A Hirose and Z-G Hou and R M Kil), Springer, ICONIP, 2013 (inproceedings)

Web [BibTex]

2013

Web [BibTex]


no image
Domain Generalization via Invariant Feature Representation

Muandet, K., Balduzzi, D., Schölkopf, B.

In Proceedings of the 30th International Conference on Machine Learning, W&CP 28(1), pages: 10-18, (Editors: S Dasgupta and D McAllester), JMLR, ICML, 2013, Volume 28, number 1 (inproceedings)

Web [BibTex]

Web [BibTex]


no image
Learning Sequential Motor Tasks

Daniel, C., Neumann, G., Peters, J.

In Proceedings of 2013 IEEE International Conference on Robotics and Automation (ICRA 2013), 2013 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Information-Theoretic Motor Skill Learning

Neumann, G., Kupcsik, A., Deisenroth, M., Peters, J.

In Proceedings of the 27th AAAI 2013, Workshop on Intelligent Robotic Systems (AAAI 2013), 2013 (inproceedings)

[BibTex]

[BibTex]


no image
Measuring Statistical Dependence via the Mutual Information Dimension

Sugiyama, M., Borgwardt, KM.

In Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI 2013), pages: 1692-1698, (Editors: Francesca Rossi), AAAI Press, Menlo Park, California, IJCAI, 2013 (inproceedings)

[BibTex]

[BibTex]


no image
Analytical probabilistic proton dose calculation and range uncertainties

Bangert, M., Hennig, P., Oelfke, U.

In 17th International Conference on the Use of Computers in Radiation Therapy, pages: 6-11, (Editors: A. Haworth and T. Kron), ICCR, 2013 (inproceedings)

[BibTex]

[BibTex]


no image
Adaptivity to Local Smoothness and Dimension in Kernel Regression

Kpotufe, S., Garg, V.

In Advances in Neural Information Processing Systems 26, pages: 3075-3083, (Editors: C.J.C. Burges and L. Bottou and M. Welling and Z. Ghahramani and K.Q. Weinberger), 27th Annual Conference on Neural Information Processing Systems (NIPS), 2013 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Statistical analysis of coupled time series with Kernel Cross-Spectral Density operators

Besserve, M., Logothetis, N., Schölkopf, B.

In Advances in Neural Information Processing Systems 26, pages: 2535-2543, (Editors: C.J.C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger), 27th Annual Conference on Neural Information Processing Systems (NIPS), 2013 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
It is all in the noise: Efficient multi-task Gaussian process inference with structured residuals

Rakitsch, B., Lippert, C., Borgwardt, KM., Stegle, O.

In Advances in Neural Information Processing Systems 26, pages: 1466-1474, (Editors: C.J.C. Burges and L. Bottou and M. Welling and Z. Ghahramani and K.Q. Weinberger), 27th Annual Conference on Neural Information Processing Systems (NIPS), 2013 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Comparative Classifier Evaluation for Web-Scale Taxonomies Using Power Law

Babbar, R., Partalas, I., Metzig, C., Gaussier, E., Amini, M.

In The Semantic Web: ESWC 2013 Satellite Events, Lecture Notes in Computer Science, Vol. 7955 , pages: 310-311, (Editors: P Cimiano and M Fernández and V Lopez and S Schlobach and J Völker), Springer, ESWC, 2013 (inproceedings)

Web [BibTex]

Web [BibTex]


no image
Model-based Imitation Learning by Probabilistic Trajectory Matching

Englert, P., Paraschos, A., Peters, J., Deisenroth, M.

In Proceedings of 2013 IEEE International Conference on Robotics and Automation (ICRA 2013), pages: 1922-1927, 2013 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Towards neurofeedback for improving visual attention

Zander, T., Battes, B., Schölkopf, B., Grosse-Wentrup, M.

In Proceedings of the Fifth International Brain-Computer Interface Meeting: Defining the Future, pages: Article ID: 086, (Editors: J.d.R. Millán, S. Gao, R. Müller-Putz, J.R. Wolpaw, and J.E. Huggins), Verlag der Technischen Universität Graz, 5th International Brain-Computer Interface Meeting, 2013, Article ID: 086 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
A Guided Hybrid Genetic Algorithm for Feature Selection with Expensive Cost Functions

Jung, M., Zscheischler, J.

In Proceedings of the International Conference on Computational Science, 18, pages: 2337 - 2346, Procedia Computer Science, (Editors: Alexandrov, V and Lees, M and Krzhizhanovskaya, V and Dongarra, J and Sloot, PMA), Elsevier, Amsterdam, Netherlands, ICCS, 2013 (inproceedings)

Web DOI [BibTex]

Web DOI [BibTex]


no image
Learning responsive robot behavior by imitation

Ben Amor, H., Vogt, D., Ewerton, M., Berger, E., Jung, B., Peters, J.

In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2013), pages: 3257-3264, IEEE, 2013 (inproceedings)

DOI [BibTex]

DOI [BibTex]


no image
Learning Skills with Motor Primitives

Peters, J., Kober, J., Mülling, K., Kroemer, O., Neumann, G.

In Proceedings of the 16th Yale Workshop on Adaptive and Learning Systems, 2013 (inproceedings)

[BibTex]

[BibTex]


no image
Scalable Influence Estimation in Continuous-Time Diffusion Networks

Du, N., Song, L., Gomez Rodriguez, M., Zha, H.

In Advances in Neural Information Processing Systems 26, pages: 3147-3155, (Editors: C.J.C. Burges and L. Bottou and M. Welling and Z. Ghahramani and K.Q. Weinberger), 27th Annual Conference on Neural Information Processing Systems (NIPS), 2013 (inproceedings)

PDF PDF [BibTex]

PDF PDF [BibTex]


no image
Rapid Distance-Based Outlier Detection via Sampling

Sugiyama, M., Borgwardt, KM.

In Advances in Neural Information Processing Systems 26, pages: 467-475, (Editors: C.J.C. Burges and L. Bottou and M. Welling and Z. Ghahramani and K.Q. Weinberger), 27th Annual Conference on Neural Information Processing Systems (NIPS), 2013 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Probabilistic Movement Primitives

Paraschos, A., Daniel, C., Peters, J., Neumann, G.

In Advances in Neural Information Processing Systems 26, pages: 2616-2624, (Editors: C.J.C. Burges and L. Bottou and M. Welling and Z. Ghahramani and K.Q. Weinberger), 27th Annual Conference on Neural Information Processing Systems (NIPS), 2013 (inproceedings)

PDF PDF [BibTex]

PDF PDF [BibTex]


no image
Causal Inference on Time Series using Restricted Structural Equation Models

Peters, J., Janzing, D., Schölkopf, B.

In Advances in Neural Information Processing Systems 26, pages: 154-162, (Editors: C.J.C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger), 27th Annual Conference on Neural Information Processing Systems (NIPS), 2013 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Regression-tree Tuning in a Streaming Setting

Kpotufe, S., Orabona, F.

In Advances in Neural Information Processing Systems 26, pages: 1788-1796, (Editors: C.J.C. Burges and L. Bottou and M. Welling and Z. Ghahramani and K.Q. Weinberger), 27th Annual Conference on Neural Information Processing Systems (NIPS), 2013 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
Density estimation from unweighted k-nearest neighbor graphs: a roadmap

von Luxburg, U., Alamgir, M.

In Advances in Neural Information Processing Systems 26, pages: 225-233, (Editors: C.J.C. Burges and L. Bottou and M. Welling and Z. Ghahramani and K.Q. Weinberger), 27th Annual Conference on Neural Information Processing Systems (NIPS), 2013 (inproceedings)

PDF [BibTex]

PDF [BibTex]


no image
PAC-Bayes-Empirical-Bernstein Inequality

Tolstikhin, I. O., Seldin, Y.

In Advances in Neural Information Processing Systems 26, pages: 109-117, (Editors: C.J.C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger), 27th Annual Conference on Neural Information Processing Systems (NIPS), 2013 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


no image
PLAL: Cluster-based active learning

Urner, R., Wulff, S., Ben-David, S.

In Proceedings of the 26th Annual Conference on Learning Theory, 30, pages: 376-397, (Editors: Shalev-Shwartz, S. and Steinwart, I.), JMLR, COLT, 2013 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


no image
Monochromatic Bi-Clustering

Wulff, S., Urner, R., Ben-David, S.

In Proceedings of the 30th International Conference on Machine Learning, 28, pages: 145-153, (Editors: Dasgupta, S. and McAllester, D.), JMLR, ICML, 2013 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


no image
Significance of variable height-bandwidth group delay filters in the spectral reconstruction of speech

Devanshu, A., Raj, A., Hegde, R. M.

INTERSPEECH 2013, 14th Annual Conference of the International Speech Communication Association, pages: 1682-1686, 2013 (conference)

link (url) [BibTex]

link (url) [BibTex]


no image
Generative Multiple-Instance Learning Models For Quantitative Electromyography

Adel, T., Smith, B., Urner, R., Stashuk, D., Lizotte, D. J.

In Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence, AUAI Press, UAI, 2013 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


no image
Automatic Malaria Diagnosis system

Mehrjou, A., Abbasian, T., Izadi, M.

In First RSI/ISM International Conference on Robotics and Mechatronics (ICRoM), pages: 205-211, 2013 (inproceedings)

DOI [BibTex]

DOI [BibTex]


no image
Abstraction in Decision-Makers with Limited Information Processing Capabilities

Genewein, T, Braun, DA

pages: 1-9, NIPS Workshop Planning with Information Constraints for Control, Reinforcement Learning, Computational Neuroscience, Robotics and Games, December 2013 (conference)

Abstract
A distinctive property of human and animal intelligence is the ability to form abstractions by neglecting irrelevant information which allows to separate structure from noise. From an information theoretic point of view abstractions are desirable because they allow for very efficient information processing. In artificial systems abstractions are often implemented through computationally costly formations of groups or clusters. In this work we establish the relation between the free-energy framework for decision-making and rate-distortion theory and demonstrate how the application of rate-distortion for decision-making leads to the emergence of abstractions. We argue that abstractions are induced due to a limit in information processing capacity.

link (url) [BibTex]

link (url) [BibTex]


no image
Bounded Rational Decision-Making in Changing Environments

Grau-Moya, J, Braun, DA

pages: 1-9, NIPS Workshop Planning with Information Constraints for Control, Reinforcement Learning, Computational Neuroscience, Robotics and Games, December 2013 (conference)

Abstract
A perfectly rational decision-maker chooses the best action with the highest utility gain from a set of possible actions. The optimality principles that describe such decision processes do not take into account the computational costs of finding the optimal action. Bounded rational decision-making addresses this problem by specifically trading off information-processing costs and expected utility. Interestingly, a similar trade-off between energy and entropy arises when describing changes in thermodynamic systems. This similarity has been recently used to describe bounded rational agents. Crucially, this framework assumes that the environment does not change while the decision-maker is computing the optimal policy. When this requirement is not fulfilled, the decision-maker will suffer inefficiencies in utility, that arise because the current policy is optimal for an environment in the past. Here we borrow concepts from non-equilibrium thermodynamics to quantify these inefficiencies and illustrate with simulations its relationship with computational resources.

link (url) [BibTex]

link (url) [BibTex]

2008


no image
A Predictive Model for Imitation Learning in Partially Observable Environments

Boularias, A.

In ICMLA 2008, pages: 83-90, (Editors: Wani, M. A., X.-W. Chen, D. Casasent, L. A. Kurgan, T. Hu, K. Hafeez), IEEE, Piscataway, NJ, USA, Seventh International Conference on Machine Learning and Applications, December 2008 (inproceedings)

Abstract
Learning by imitation has shown to be a powerful paradigm for automated learning in autonomous robots. This paper presents a general framework of learning by imitation for stochastic and partially observable systems. The model is a Predictive Policy Representation (PPR) whose goal is to represent the teacher‘s policies without any reference to states. The model is fully described in terms of actions and observations only. We show how this model can efficiently learn the personal behavior and preferences of an assistive robot user.

PDF Web DOI [BibTex]

2008

PDF Web DOI [BibTex]


no image
Stereo Matching for Calibrated Cameras without Correspondence

Helmke, U., Hüper, K., Vences, L.

In CDC 2008, pages: 2408-2413, IEEE Service Center, Piscataway, NJ, USA, 47th IEEE Conference on Decision and Control, December 2008 (inproceedings)

Abstract
We study the stereo matching problem for reconstruction of the location of 3D-points on an unknown surface patch from two calibrated identical cameras without using any a priori information about the pointwise correspondences. We assume that camera parameters and the pose between the cameras are known. Our approach follows earlier work for coplanar cameras where a gradient flow algorithm was proposed to match associated Gramians. Here we extend this method by allowing arbitrary poses for the cameras. We introduce an intrinsic Riemannian Newton algorithm that achieves local quadratic convergence rates. A closed form solution is presented, too. The efficiency of both algorithms is demonstrated by numerical experiments.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Joint Kernel Support Estimation for Structured Prediction

Lampert, C., Blaschko, M.

In Proceedings of the NIPS 2008 Workshop on "Structured Input - Structured Output" (NIPS SISO 2008), pages: 1-4, NIPS Workshop on "Structured Input - Structured Output" (NIPS SISO), December 2008 (inproceedings)

Abstract
We present a new technique for structured prediction that works in a hybrid generative/ discriminative way, using a one-class support vector machine to model the joint probability of (input, output)-pairs in a joint reproducing kernel Hilbert space. Compared to discriminative techniques, like conditional random elds or structured out- put SVMs, the proposed method has the advantage that its training time depends only on the number of training examples, not on the size of the label space. Due to its generative aspect, it is also very tolerant against ambiguous, incomplete or incorrect labels. Experiments on realistic data show that our method works eciently and robustly in situations for which discriminative techniques have computational or statistical problems.

PDF Web [BibTex]

PDF Web [BibTex]


no image
Metropolis Algorithms for Representative Subgraph Sampling

Hübler, C., Kriegel, H., Borgwardt, K., Ghahramani, Z.

In pages: 283-292, (Editors: Giannotti, F.), IEEE, Piscataway, NJ, USA, Eighth IEEE International Conference on Data Mining (ICDM '08) , December 2008 (inproceedings)

Abstract
While data mining in chemoinformatics studied graph data with dozens of nodes, systems biology and the Internet are now generating graph data with thousands and millions of nodes. Hence data mining faces the algorithmic challenge of coping with this significant increase in graph size: Classic algorithms for data analysis are often too expensive and too slow on large graphs. While one strategy to overcome this problem is to design novel efficient algorithms, the other is to 'reduce' the size of the large graph by sampling. This is the scope of this paper: We will present novel Metropolis algorithms for sampling a 'representative' small subgraph from the original large graph, with 'representative' describing the requirement that the sample shall preserve crucial graph properties of the original graph. In our experiments, we improve over the pioneering work of Leskovec and Faloutsos (KDD 2006), by producing representative subgraph samples that are both smaller and of higher quality than those produced by other methods from the literature.

Web DOI [BibTex]

Web DOI [BibTex]


no image
Frequent Subgraph Retrieval in Geometric Graph Databases

Nowozin, S., Tsuda, K.

In ICDM 2008, pages: 953-958, (Editors: Giannotti, F. , D. Gunopulos, F. Turini, C. Zaniolo, N. Ramakrishnan, X. Wu), IEEE Computer Society, Los Alamitos, CA, USA, 8th IEEE International Conference on Data Mining, December 2008 (inproceedings)

Abstract
Discovery of knowledge from geometric graph databases is of particular importance in chemistry and biology, because chemical compounds and proteins are represented as graphs with 3D geometric coordinates. In such applications, scientists are not interested in the statistics of the whole database. Instead they need information about a novel drug candidate or protein at hand, represented as a query graph. We propose a polynomial-delay algorithm for geometric frequent subgraph retrieval. It enumerates all subgraphs of a single given query graph which are frequent geometric $epsilon$-subgraphs under the entire class of rigid geometric transformations in a database. By using geometric$epsilon$-subgraphs, we achieve tolerance against variations in geometry. We compare the proposed algorithm to gSpan on chemical compound data, and we show that for a given minimum support the total number of frequent patterns is substantially limited by requiring geometric matching. Although the computation time per pattern is lar ger than for non-geometric graph mining,the total time is within a reasonable level even for small minimum support.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Block Iterative Algorithms for Non-negative Matrix Approximation

Sra, S.

In ICDM 2008, pages: 1037-1042, (Editors: Giannotti, F. , D. Gunopulos, F. Turini, C. Zaniolo, N. Ramakrishnan, X. Wu), IEEE Service Center, Piscataway, NJ, USA, Eighth IEEE International Conference on Data Mining, December 2008 (inproceedings)

Abstract
In this paper we present new algorithms for non-negative matrix approximation (NMA), commonly known as the NMF problem. Our methods improve upon the well-known methods of Lee & Seung~cite{lee00} for both the Frobenius norm as well the Kullback-Leibler divergence versions of the problem. For the latter problem, our results are especially interesting because it seems to have witnessed much lesser algorithmic progress as compared to the Frobenius norm NMA problem. Our algorithms are based on a particular textbf {block-iterative} acceleration technique for EM, which preserves the multiplicative nature of the updates and also ensures monotonicity. Furthermore, our algorithms also naturally apply to the Bregman-divergence NMA algorithms of~cite{suv.nips}. Experimentally, we show that our algorithms outperform the traditional Lee/Seung approach most of the time.

Web DOI [BibTex]

Web DOI [BibTex]


no image
A Bayesian Approach to Switching Linear Gaussian State-Space Models for Unsupervised Time-Series Segmentation

Chiappa, S.

In ICMLA 2008, pages: 3-9, (Editors: Wani, M. A., X.-W. Chen, D. Casasent, L. Kurgan, T. Hu, K. Hafeez), IEEE Computer Society, Los Alamitos, CA, USA, 7th International Conference on Machine Learning and Applications, December 2008 (inproceedings)

Abstract
Time-series segmentation in the fully unsupervised scenario in which the number of segment-types is a priori unknown is a fundamental problem in many applications. We propose a Bayesian approach to a segmentation model based on the switching linear Gaussian state-space model that enforces a sparse parametrization, such as to use only a small number of a priori available different dynamics to explain the data. This enables us to estimate the number of segment-types within the model, in contrast to previous non-Bayesian approaches where training and comparing several separate models was required. As the resulting model is computationally intractable, we introduce a variational approximation where a reformulation of the problem enables the use of efficient inference algorithms.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Infinite Kernel Learning

Gehler, P., Nowozin, S.

In Proceedings of the NIPS 2008 Workshop on "Kernel Learning: Automatic Selection of Optimal Kernels", pages: 1-4, NIPS Workshop on "Kernel Learning: Automatic Selection of Optimal Kernels" (LK ASOK´08), December 2008 (inproceedings)

Abstract
In this paper we build upon the Multiple Kernel Learning (MKL) framework and in particular on [1] which generalized it to infinitely many kernels. We rewrite the problem in the standard MKL formulation which leads to a Semi-Infinite Program. We devise a new algorithm to solve it (Infinite Kernel Learning, IKL). The IKL algorithm is applicable to both the finite and infinite case and we find it to be faster and more stable than SimpleMKL [2]. Furthermore we present the first large scale comparison of SVMs to MKL on a variety of benchmark datasets, also comparing IKL. The results show two things: a) for many datasets there is no benefit in using MKL/IKL instead of the SVM classifier, thus the flexibility of using more than one kernel seems to be of no use, b) on some datasets IKL yields massive increases in accuracy over SVM/MKL due to the possibility of using a largely increased kernel set. For those cases parameter selection through Cross-Validation or MKL is not applicable.

PDF Web [BibTex]

PDF Web [BibTex]


no image
Prediction-Directed Compression of POMDPs

Boularias, A., Izadi, M., Chaib-Draa, B.

In ICMLA 2008, pages: 99-105, (Editors: Wani, M. A., X.-W. Chen, D. Casasent, L. A. Kurgan, T. Hu, K. Hafeez), IEEE, Piscataway, NJ, USA, Seventh International Conference on Machine Learning and Applications, December 2008 (inproceedings)

Abstract
High dimensionality of belief space in partially observable Markov decision processes (POMDPs) is one of the major causes that severely restricts the applicability of this model. Previous studies have demonstrated that the dimensionality of a POMDP can eventually be reduced by transforming it into an equivalent predictive state representation (PSR). In this paper, we address the problem of finding an approximate and compact PSR model corresponding to a given POMDP model. We formulate this problem in an optimization framework. Our algorithm tries to minimize the potential error that missing some core tests may cause. We also present an empirical evaluation on benchmark problems, illustrating the performance of this approach.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Iterative Subgraph Mining for Principal Component Analysis

Saigo, H., Tsuda, K.

In ICDM 2008, pages: 1007-1012, (Editors: Giannotti, F. , D. Gunopulos, F. Turini, C. Zaniolo, N. Ramakrishnan, X. Wu), IEEE Computer Society, Los Alamitos, CA, USA, IEEE International Conference on Data Mining, December 2008 (inproceedings)

Abstract
Graph mining methods enumerate frequent subgraphs efficiently, but they are not necessarily good features for machine learning due to high correlation among features. Thus it makes sense to perform principal component analysis to reduce the dimensionality and create decorrelated features. We present a novel iterative mining algorithm that captures informative patterns corresponding to major entries of top principal components. It repeatedly calls weighted substructure mining where example weights are updated in each iteration. The Lanczos algorithm, a standard algorithm of eigendecomposition, is employed to update the weights. In experiments, our patterns are shown to approximate the principal components obtained by frequent mining.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Probabilistic Inference for Fast Learning in Control

Rasmussen, CE., Deisenroth, MP.

In EWRL 2008, pages: 229-242, (Editors: Girgin, S. , M. Loth, R. Munos, P. Preux, D. Ryabko), Springer, Berlin, Germany, 8th European Workshop on Reinforcement Learning, November 2008 (inproceedings)

Abstract
We provide a novel framework for very fast model-based reinforcement learning in continuous state and action spaces. The framework requires probabilistic models that explicitly characterize their levels of confidence. Within this framework, we use flexible, non-parametric models to describe the world based on previously collected experience. We demonstrate learning on the cart-pole problem in a setting where we provide very limited prior knowledge about the task. Learning progresses rapidly, and a good policy is found after only a hand-full of iterations.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Policy Learning: A Unified Perspective with Applications in Robotics

Peters, J., Kober, J., Nguyen-Tuong, D.

In EWRL 2008, pages: 220-228, (Editors: Girgin, S. , M. Loth, R. Munos, P. Preux, D. Ryabko), Springer, Berlin, Germany, 8th European Workshop on Reinforcement Learning, November 2008 (inproceedings)

Abstract
Policy Learning approaches are among the best suited methods for high-dimensional, continuous control systems such as anthropomorphic robot arms and humanoid robots. In this paper, we show two contributions: firstly, we show a unified perspective which allows us to derive several policy learning algorithms from a common point of view, i.e, policy gradient algorithms, natural-gradient algorithms and EM-like policy learning. Secondly, we present several applications to both robot motor primitive learning as well as to robot control in task space. Results both from simulation and several different real robots are shown.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Two-Channel Control for Scaled Teleoperation

Son, HI., Lee, DY.

In International Conference on Control, Automation and Systems, pages: 1284-1289, IEEE, Piscataway, NJ, USA, International Conference on Control, Automation and Systems (ICCAS), October 2008 (inproceedings)

Abstract
There is a trade-off between stability and performance in haptic control systems. In this paper, a stability and performance analysis is presented for a scaled teleoperation system in an effort to increase the performance of the system while maintaining the stability. The stability is quantitatively defined as a metric using Llewellynpsilas absolute stability criterion. Position tracking and kinesthetic perception are used as the performance indices. The analysis is carried out using various scaling factors and impedances of human and environment. A two-channel position-position (PP) controller and a two-channel force-position (FP) controller are applied for the analysis and simulation.

Web DOI [BibTex]

Web DOI [BibTex]


no image
Learning to Localize Objects with Structured Output Regression

Blaschko, MB., Lampert, CH.

In ECCV 2008, pages: 2-15, (Editors: Forsyth, D. A., P. H.S. Torr, A. Zisserman), Springer, Berlin, Germany, 10th European Conference on Computer Vision, October 2008, Best Student Paper Award (inproceedings)

Abstract
Sliding window classifiers are among the most successful and widely applied techniques for object localization. However, training is typically done in a way that is not specific to the localization task. First a binary classifier is trained using a sample of positive and negative examples, and this classifier is subsequently applied to multiple regions within test images. We propose instead to treat object localization in a principled way by posing it as a problem of predicting structured data: we model the problem not as binary classification, but as the prediction of the bounding box of objects located in images. The use of a joint-kernel framework allows us to formulate the training procedure as a generalization of an SVM, which can be solved efficiently. We further improve computational efficiency by using a branch-and-bound strategy for localization during both training and testing. Experimental evaluation on the PASCAL VOC and TU Darmstadt datasets show that the structured training procedure improves pe rformance over binary training as well as the best previously published scores.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Automatic Image Colorization Via Multimodal Predictions

Charpiat, G., Hofmann, M., Schölkopf, B.

In Computer Vision - ECCV 2008, Lecture Notes in Computer Science, Vol. 5304, pages: 126-139, (Editors: DA Forsyth and PHS Torr and A Zisserman), Springer, Berlin, Germany, 10th European Conference on Computer Vision, October 2008 (inproceedings)

Abstract
We aim to color automatically greyscale images, without any manual intervention. The color proposition could then be interactively corrected by user-provided color landmarks if necessary. Automatic colorization is nontrivial since there is usually no one-to-one correspondence between color and local texture. The contribution of our framework is that we deal directly with multimodality and estimate, for each pixel of the image to be colored, the probability distribution of all possible colors, instead of choosing the most probable color at the local level. We also predict the expected variation of color at each pixel, thus defining a nonuniform spatial coherency criterion. We then use graph cuts to maximize the probability of the whole colored image at the global level. We work in the L-a-b color space in order to approximate the human perception of distances between colors, and we use machine learning tools to extract as much information as possible from a dataset of colored examples. The resulting algorithm is fast, designed to be more robust to texture noise, and is above all able to deal with ambiguity, in contrary to previous approaches.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Nonparametric Independence Tests: Space Partitioning and Kernel Approaches

Gretton, A., Györfi, L.

In ALT08, pages: 183-198, (Editors: Freund, Y. , L. Györfi, G. Turán, T. Zeugmann), Springer, Berlin, Germany, 19th International Conference on Algorithmic Learning Theory (ALT08), October 2008 (inproceedings)

Abstract
Three simple and explicit procedures for testing the independence of two multi-dimensional random variables are described. Two of the associated test statistics (L1, log-likelihood) are defined when the empirical distribution of the variables is restricted to finite partitions. A third test statistic is defined as a kernel-based independence measure. All tests reject the null hypothesis of independence if the test statistics become large. The large deviation and limit distribution properties of all three test statistics are given. Following from these results, distributionfree strong consistent tests of independence are derived, as are asymptotically alpha-level tests. The performance of the tests is evaluated experimentally on benchmark data.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Automatic 3D Face Reconstruction from Single Images or Video

Breuer, P., Kim, K., Kienzle, W., Schölkopf, B., Blanz, V.

In FG 2008, pages: 1-8, IEEE Computer Society, Los Alamitos, CA, USA, 8th IEEE International Conference on Automatic Face and Gesture Recognition, September 2008 (inproceedings)

Abstract
This paper presents a fully automated algorithm for reconstructing a textured 3D model of a face from a single photograph or a raw video stream. The algorithm is based on a combination of Support Vector Machines (SVMs) and a Morphable Model of 3D faces. After SVM face detection, individual facial features are detected using a novel regression- and classification-based approach, and probabilistically plausible configurations of features are selected to produce a list of candidates for several facial feature positions. In the next step, the configurations of feature points are evaluated using a novel criterion that is based on a Morphable Model and a combination of linear projections. To make the algorithm robust with respect to head orientation, this process is iterated while the estimate of pose is refined. Finally, the feature points initialize a model-fitting procedure of the Morphable Model. The result is a highresolution 3D surface model.

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Kernel Measures of Conditional Dependence

Fukumizu, K., Gretton, A., Sun, X., Schölkopf, B.

In Advances in neural information processing systems 20, pages: 489-496, (Editors: JC Platt and D Koller and Y Singer and S Roweis), Curran, Red Hook, NY, USA, 21st Annual Conference on Neural Information Processing Systems (NIPS), September 2008 (inproceedings)

Abstract
We propose a new measure of conditional dependence of random variables, based on normalized cross-covariance operators on reproducing kernel Hilbert spaces. Unlike previous kernel dependence measures, the proposed criterion does not depend on the choice of kernel in the limit of infinite data, for a wide class of kernels. At the same time, it has a straightforward empirical estimate with good convergence behaviour. We discuss the theoretical properties of the measure, and demonstrate its application in experiments.

PDF Web [BibTex]

PDF Web [BibTex]


no image
An Analysis of Inference with the Universum

Sinz, F., Chapelle, O., Agarwal, A., Schölkopf, B.

In Advances in neural information processing systems 20, pages: 1369-1376, (Editors: JC Platt and D Koller and Y Singer and S Roweis), Curran, Red Hook, NY, USA, 21st Annual Conference on Neural Information Processing Systems (NIPS), September 2008 (inproceedings)

Abstract
We study a pattern classification algorithm which has recently been proposed by Vapnik and coworkers. It builds on a new inductive principle which assumes that in addition to positive and negative data, a third class of data is available, termed the Universum. We assay the behavior of the algorithm by establishing links with Fisher discriminant analysis and oriented PCA, as well as with an SVM in a projected subspace (or, equivalently, with a data-dependent reduced kernel). We also provide experimental results.

PDF Web [BibTex]

PDF Web [BibTex]


no image
Learning with Transformation Invariant Kernels

Walder, C., Chapelle, O.

In Advances in neural information processing systems 20, pages: 1561-1568, (Editors: Platt, J. C., D. Koller, Y. Singer, S. Roweis), Curran, Red Hook, NY, USA, Twenty-First Annual Conference on Neural Information Processing Systems (NIPS), September 2008 (inproceedings)

Abstract
This paper considers kernels invariant to translation, rotation and dilation. We show that no non-trivial positive definite (p.d.) kernels exist which are radial and dilation invariant, only conditionally positive definite (c.p.d.) ones. Accordingly, we discuss the c.p.d. case and provide some novel analysis, including an elementary derivation of a c.p.d. representer theorem. On the practical side, we give a support vector machine (s.v.m.) algorithm for arbitrary c.p.d. kernels. For the thinplate kernel this leads to a classifier with only one parameter (the amount of regularisation), which we demonstrate to be as effective as an s.v.m. with the Gaussian kernel, even though the Gaussian involves a second parameter (the length scale).

PDF Web [BibTex]

PDF Web [BibTex]


no image
Episodic Reinforcement Learning by Logistic Reward-Weighted Regression

Wierstra, D., Schaul, T., Peters, J., Schmidhuber, J.

In ICANN 2008, pages: 407-416, (Editors: Kurkova-Pohlova, V. , R. Neruda, J. Koutnik), Springer, Berlin, Germany, 18th International Conference on Artificial Neural Networks, September 2008 (inproceedings)

Abstract
It has been a long-standing goal in the adaptive control community to reduce the generically difficult, general reinforcement learning (RL) problem to simpler problems solvable by supervised learning. While this approach is today’s standard for value function-based methods, fewer approaches are known that apply similar reductions to policy search methods. Recently, it has been shown that immediate RL problems can be solved by reward-weighted regression, and that the resulting algorithm is an expectation maximization (EM) algorithm with strong guarantees. In this paper, we extend this algorithm to the episodic case and show that it can be used in the context of LSTM recurrent neural networks (RNNs). The resulting RNN training algorithm is equivalent to a weighted self-modeling supervised learning technique. We focus on partially observable Markov decision problems (POMDPs) where it is essential that the policy is nonstationary in order to be optimal. We show that this new reward-weighted logistic regression u sed in conjunction with an RNN architecture can solve standard benchmark POMDPs with ease.

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]